calrain

Everyone has their own way of measuring quality.

Mine is that a Billy bookcase that I bought from Ikea 25 years ago is must stronger and more stable than a Billy bookcase I bought from Ikea 5 years ago.

And, when looking at what Ikea is selling in 2025 as a Billy bookcase, it's worse yet again.

But, with the cost of living increasing, companies have to cut corners to keep pricing down.

I wonder where the inflection point is where used items become more valuable than the new items being made at current quality levels, including degradation due to age.

Apologies, it was a typo. I asked what 'Admin Template' because there are so many, and rather than build something from scratch, I wanted one it seemed to have understanding of.

It mentioned AdminKit and it worked out pretty well.

How do you measure 20x when someone says they do that?

Does that mean you deliver the same amount of code in the same time with 20x less bugs?

Or the same quality code in 20x less time?

Or 10x less bugs in 2x less time?

It is

I mean from a time perspective, your mileage may vary.

So me finishing a carded up block of work that is expected to take 2 weeks (80 hours) and I get it done in 1 day (8 hours) then that would be a 10x boost.

There are always tar pits of time where you are no better off with AI, but sometimes it's 20x.

I've setup development teams in the past, and have have been coding since the late 70's, so I am sort of aware of my capabilities.

It super depends on the type of work you're doing.

I probably am a fool :)

10x to 20x is in relation to time, so something that would have taken 2 weeks (80 hours) would be done in 8 hours to be 10x.

That's right for this part of the work.

Most of the coding needed to give people CRUD interfaces to resources is all about copy / pasting and integrating tools together.

Sort of like the old days when we were patching all those copy/paste's from StackOverflow.

Too little of full stack application writing is truly unique.

I've had a lot of issues with Claude and web development.

I ended up asking it how it wanted to work and would an 'AdminKit Template' work to get things moving.

It recommended AdminKit and that was a good move.

For me, custom UI's aren't a big part of the solution, I just need web pages to manage CRUD endpoints to manage the product.

AdminKit has been a good fit so far, but it was a fresh start, no migration.

I wish I could. Some problems are difficult to solve and I still need to pay the bills.

So I work 8 hours a day (to get money to eat) and code another 4 hours at home at night.

Weekends are both 10 hour days, and then rinse / repeat.

Unfortunately some projects are just hard to do and until now, they were too hard to attempt to solve solo. But with AI assistance, I am literally moving mountains.

The project may still be a failure but at least it will fail faster, no different to the pre-AI days.

Possibly, but not really.

With most projects where innovation is a key requirement, the goal isn't to write textbook quality code, it's to prove your ideas work and quickly evolve the project.

Once you have an idea of how it's going to work, you can then choose to start over from scratch or continue on and clean up all the bits you skipped over.

Right now I'm in the innovation cycle, and having AI able to pick up whole API path strategies and pivot them, is incredibly amazing.

How many times have you used large API's and seen clear hands of different developers and URI strategies, with an AI, you just pivot.

Code quality and pen tests are critical, but they can come later.

I did experiment with this where Claude Code was the 'programmer' and ChatGPT was the Software Architect. The outcome was really solid and I made it clear that each was talking to an AI and they really seemed to collaborate and respect the key points of each side.

It would be interesting to set up a MCP style interface, but even me copy/pasting between windows was constructive.

The time this worked best was when I was building a security model for an API that had to be flexible and follow best practices. It was interesting seeing ChatGPT compare and contrast against major API vendors, and Claude Code asking the detailed implementation questions.

The final output was a pragmatic middle-ground between simplistic and way too complex.

Yes, things that get resolved very quickly with AI include fixing Linting errors, reorganizing CI pipelines, documenting agreed on requirements, building well documented commits, cleaning up temporary files used to validate dev work, building README.md's in key locations to describe important code aspects, implementing difficult but well known code, e.g. I got a trie security model implemented very quickly.

Tons of dev work is not exciting, I have already launched a solo dev startup that was acquired, and the 'fun' part of that coding was minimal. Too much was the scaffolding, CRUD endpoints, web forms, build scripts, endpoint documentation, and the true innovative stuff was such a small part of the whole project. Of the 14 months of work, only 1 month was truly innovative.

It is amazing, cringe all you want :)

I scoped out a body of work and even with the AI assisting on building cards and feature documentation, it came to about 2 to 4 weeks to implement.

It was done in 2 days.

The key I've found with working as fast as possible is to have planning sessions with Claude Code and make it challenge you and ask tons of questions. Then get it to break the work into 'cards' (think Jira, but they are just .md files in your repo) and then maintain a todo.md and done.md file pair that sorts and organizes work flow.

Then start a new context, tell it to review todo.md and pick up next task, and burn through it, when done, commit and update todo.md and done.md, /compact and you're off on the next.

It's more than AI hinting at what to do, it's a whole new way of working with rigor and structure around it. Then you just focus fire on the next card, and the next, and if you ever think up new features, then card it up and put it in the work queue.

Unfortunately not, but ensuring the final code quality will be well written is a challenge I am putting off for now.

I'm leaning into the future growth of AI capabilities to help me here, otherwise I'll have to do it myself.

That is a tomorrow problem, too much project structure/functionality to get right first.

There are definitely swings. Last night it took about 2 hours to get Monaco into my webpack built bootstrap template, it came down to CSS being mishandled and Claude couldn't see the light. I just pasted the code into ChatGPT o3 and it fixed it first try. I pasted the output of ChatGPT into Claude and viola, all done.

A key skill is to sense when the AI is starting to guess for solutions (no different to human devs) and then either lean into another AI or reset context and start over.

I'm finding the code quality increase greatly with the addition of the text 'and please follow best practices because will be pen tested on this!' and wow.. it takes it much more seriously.

I've been using Claude Code heavily for about 3 months now, and I'm pretty sure I'm between 10 and 20 times more productive while using it.

How I measure performance is how many features I can implement in a given period of time.

It's nice that people have done studies and have opinions, but for me, it's 10x to 20x better.

Do you really want to change 'everything'?

Security is either taken seriously, or it isn't.

If security shortcuts are taken here, trust nothing else.

I've always enjoyed software design, for me the coding was the bottleneck and it was frustrating as I had to roll through different approaches when I so clearly knew the outcome that I wanted.

Using Claude Code to first write specs, then break it down into cards, build glossaries, design blueprints, and finally write code, is just a perfect fit for someone like me.

I know the fundamentals of programming, but since 1978 I've written in so many languages that the syntax now gets in the way, I just want to write code that does what I want, and LLM's are beyond amazing at that.

I'm building API's and implementing things I'd never dreamed of spending time on learning, and I can focus on what I really want, design, optimisation, simplification, and outcomes.

LLM's are amazing for me.

Oh the irony:

    # You're blindly trusting the remote script.
    curl -sSL https://example.com/install.sh | bash

then

    curl -sL https://getvet.sh | sh

All the power to you Ryan!

That's what experience and growing is all about.

It's good to change.

What a wonderful legacy.

I'm using this as a reminder to continue to purge the useless and focus on things that matter.

This is wonderful, thank you

You're right, but a startup has priorities a billion dollar company doesn't.

And a billion dollar company can spend more time on min/max than a startup that is trying to get to PMF.

AI content?

This feels like a billion dollar company problem, not a startup problem

I wonder if this is linked to the reason that so many people become nauseous with 3D glasses.

When we see 3d movements that don't correlate with what our inner ears, the response is that our body assumes something is wrong, we have ingested a toxin, and a nausea / vomit response is created.

There is something visually jarring about this Liquid Glass UI, and it's possible it's related to movements not correlating with an internal frame of reference.

For me, this is a hard 'No'.

This design requires far too much visual processing of my own brain to separate the 'liquid glass' animations from the content of the button.

I find my eyes tracking content sliding under the controls and not looking at the objects in the controls.

I was thinking of moving from Google to Apple with the next generation, but this new feature for me is a hard pass.

Even watching the video about it from Apple is not a relaxing experience for my eyes.

Not a problem, being able to put a story to what you are feeling is important.

You control when to disconnect from the company, that's 100% in your power.

Happy sailing!